MCP endpoint
OperationalPOST /mcp answers a tools/list over Streamable HTTP, signed in as the probe.
2026-07-0492.73% over 1 sampled daytoday
Status · Model Context Protocol
Plumbline status
Components
Every bar is one UTC day of recorded samples. The last 90 days. Recording started 2026-10-01, so the earlier days were never sampled and are shown as gaps. A day that was never sampled is a gap, not a clean day.
Verification engine
OperationalThe upstream Plumbline Worker that decides every control.
2026-07-04100% over 1 sampled daytoday
Document extraction
OperationalA model key is configured, so documents can be transcribed.
2026-07-04100% over 1 sampled daytoday
Platform
OperationalGET /api/health on the Plumbline Platform, the signed-in workspace application at PLATFORM_URL.
2026-07-0491.82% over 1 sampled daytoday
Platform database
OperationalPostgres answers SELECT 1 through the Platform's own connection pool within 2 seconds.
2026-07-0490% over 1 sampled daytoday
Platform workspaces
OperationalThe workspaces table holds at least one row, read through the Platform's own connection pool.
2026-07-0490% over 1 sampled daytoday
Platform agent
OperationalThe chat transcript table answers a read and the agent's model replies to a call made with the agent's API key; the probe makes that call at most once every 5 minutes and reuses the result in between.
2026-07-0490% over 1 sampled daytoday
Response time
How long each probe took over the last 24 hours, one bar per hour: the solid bar is p50 and the pale one p95. Only successful probes count, so a failed probe appears in the uptime bars above and never as a fast response here.
MCP endpoint
p50 73 ms · p95 141 ms24 hours agoscaled to 149 msnow
Verification engine
p50 231 ms · p95 371 ms24 hours agoscaled to 410 msnow
Document extraction
p50 2 ms · p95 2 ms24 hours agoscaled to 3 msnow
Platform
p50 86 ms · p95 139 ms24 hours agoscaled to 209 msnow
Platform database
p50 91 ms · p95 2330 ms24 hours agoscaled to 3749 msnow
Platform workspaces
p50 90 ms · p95 2330 ms24 hours agoscaled to 3748 msnow
Platform agent
p50 90 ms · p95 2330 ms24 hours agoscaled to 3748 msnow
Incidents
An incident opens when a component fails several samples in a row and closes when it answers again. Start, end, and duration come from the samples. Any update below was written by a human and is shown exactly as typed.
Platform agent — error
No update has been written for this incident.
Platform workspaces — error
No update has been written for this incident.
Platform database — error
No update has been written for this incident.
Platform — unreachable
No update has been written for this incident.
MCP endpoint — error
No update has been written for this incident.
How this page is measured
This page holds counts and timings only: no evidence, no run ids, no client identifiers, no addresses. Plumbline is advisory. A human makes every funding decision.